collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors

Di Hu, Kun Li, Haojie Rao +6

Accurate prediction of molecular properties underpins drug discovery and material design, yet even state-of-the-art models remain vulnerable to localized failure modes that aggrega…

cs.LG2026

Rethinking Molecular OOD Generalization via Target-Aware Source Selection

Zhuohao Lin, Kun Li, Jiameng Chen +4

Robust prediction of molecular properties under extreme out-of-distribution (OOD) scenarios is a pivotal bottleneck in AI-driven drug discovery. Current scaffold-splitting protocol…

cs.LG2026

Variational Bayesian Flow Network for Graph Generation

Yida Xiong, Jiameng Chen, Xiuwen Gong +3

Graph generation aims to sample discrete node and edge attributes while satisfying coupled structural constraints. Diffusion models for graphs often adopt largely factorized forwar…

cs.LG2025

FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation

Jiameng Chen, Yida Xiong, Kun Li +4

Computational antibody design holds immense promise for therapeutic discovery, yet existing generative models are fundamentally limited by two core challenges: (i) a lack of dynami…

cs.LG2025

Transport-Coupled Bayesian Flows for Molecular Graph Generation

Yida Xiong, Jiameng Chen, Kun Li +4

Molecular graph generation (MGG) is essentially a multi-class generative task, aimed at predicting categories of atoms and bonds under strict chemical and structural constraints. H…

cs.LG2025

BSL: A Unified and Generalizable Multitask Learning Platform for Virtual Drug Discovery from Design to Synthesis

Kun Li, Zhennan Wu, Yida Xiong +8

Drug discovery is of great social significance in safeguarding human health, prolonging life, and addressing the challenges of major diseases. In recent years, artificial intellige…